论文标题
连续有条件生成的对抗网络：新颖的经验损失和标签输入机制
Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms
论文作者
论文摘要
这项工作提出了连续的条件生成对抗网络（CCGAN），这是在连续的标量条件（称为回归标签）上有条件产生图像产生的第一个生成模型。现有的有条件gan（CGAN）主要是为分类条件设计的（例如，类标签）； conditioning on regression labels is mathematically distinct and raises two fundamental problems:(P1) Since there may be very few (even zero) real images for some regression labels, minimizing existing empirical versions of cGAN losses (aka empirical cGAN losses) often fails in practice;(P2) Since regression labels are scalar and infinitely many, conventional label input methods are not applicable.拟议的CCGAN分别通过（S1）重新定义现有的经验性CGAN损失以适合连续情况来解决上述问题； （S2）提出一种幼稚的标签输入（NLI）方法和改进的标签输入（ILI）方法，以将回归标签纳入发生器和歧视器。 （S1）中的重新制作导致了两种新型的经验歧视损失，分别称为硬化歧视损失（HVDL）和软化替代歧视器损失（SVDL），以及一种新颖的经验发生器损失。在这项工作中的轻度假设下，通过HVDL和SVDL训练的歧视器的误差界限。对于这种连续的情况，还提出了两个新的基准数据集（RC-49和Cell-200）和一个新颖的评估度量标准（滑动Fréchet成立距离）。我们在圆形2-D高斯（RC-49，UTKFACE，-2000和转向角度数据集）上进行的实验表明，CCGAN能够从给定的回归标签上从图像分布中生成多样的高质量样品。此外，在这些实验中，CCGAN在视觉和定量上都大大优于CGAN。
This work proposes the continuous conditional generative adversarial network (CcGAN), the first generative model for image generation conditional on continuous, scalar conditions (termed regression labels). Existing conditional GANs (cGANs) are mainly designed for categorical conditions (eg, class labels); conditioning on regression labels is mathematically distinct and raises two fundamental problems:(P1) Since there may be very few (even zero) real images for some regression labels, minimizing existing empirical versions of cGAN losses (aka empirical cGAN losses) often fails in practice;(P2) Since regression labels are scalar and infinitely many, conventional label input methods are not applicable. The proposed CcGAN solves the above problems, respectively, by (S1) reformulating existing empirical cGAN losses to be appropriate for the continuous scenario; and (S2) proposing a naive label input (NLI) method and an improved label input (ILI) method to incorporate regression labels into the generator and the discriminator. The reformulation in (S1) leads to two novel empirical discriminator losses, termed the hard vicinal discriminator loss (HVDL) and the soft vicinal discriminator loss (SVDL) respectively, and a novel empirical generator loss. The error bounds of a discriminator trained with HVDL and SVDL are derived under mild assumptions in this work. Two new benchmark datasets (RC-49 and Cell-200) and a novel evaluation metric (Sliding Fréchet Inception Distance) are also proposed for this continuous scenario. Our experiments on the Circular 2-D Gaussians, RC-49, UTKFace, Cell-200, and Steering Angle datasets show that CcGAN is able to generate diverse, high-quality samples from the image distribution conditional on a given regression label. Moreover, in these experiments, CcGAN substantially outperforms cGAN both visually and quantitatively.
